ARTIFICIAL INTELLIGENCE-BASED HYBRID DEEP LEARNING FRAMEWORK FOR AUTOMATED BONE CANCER DETECTION AND MULTI-STAGE CLASSIFICATION USING RADIOLOGICAL IMAGING

Abstract

With increasing concerns about antimicrobial resistance and the environmental impact of synthetic disinfectants, there is growing interest in plant-derived alternatives for surface sanitation. In this study, the fungicidal effectiveness of a newly developed herbal surface cleaner containing neem (Azadirachta indica) and lemon (Citrus limon) extracts was investigated against Aspergillus niger ATCC 16404. The formulation was evaluated using neutralization validation, appropriate positive and negative controls, and quantitative suspension testing. Concentrations ranging from 3% to 7% were assessed at contact times of 10, 20, 30, and 40 minutes, with all tests performed in triplicate. The neutralization study confirmed that the neutralizer effectively quenched the antimicrobial activity of the formulation without affecting fungal recovery, yielding inoculum counts between 1.40 × 10⁷ and 1.52 × 10⁷ CFU/mL. Positive control results demonstrated stable fungal populations, with initial counts ranging from 1.48 × 10⁷ to 1.55 × 10⁷ CFU/mL (log₁₀ 7.17 7.19), confirming the reliability of the test system. The herbal cleaner exhibited strong antifungal activity across all tested concentrations. Complete elimination of A. niger was observed with the 3% and 7% formulations at every contact time examined, corresponding to a log reduction of 7.18. Although the 4% and 6% formulations showed slightly lower activity after 10 minutes of exposure (mean log reduction 6.88), complete fungal inactivation was achieved within 20 minutes. Statistical analysis using one-way ANOVA demonstrated significant differences among the tested concentrations and exposure times (p < 0.05), highlighting the influence of both factors on fungicidal performance. Overall, the results indicate that the neem–lemon herbal surface cleaner possesses potent antifungal properties and can serve as an effective, environmentally friendly alternative to conventional chemical disinfectants for routine surface hygiene applications.Bone cancer is a relatively uncommon but highly aggressive musculoskeletal malignancy that requires timely diagnosis to improve treatment outcomes and patient survival. Radiological imaging modalities, including X-ray, computed tomography (CT), and magnetic resonance imaging (MRI), remain fundamental for diagnosis; however, manual interpretation is time-consuming and may be influenced by inter-observer variability. Recent advances in artificial intelligence (AI) and deep learning have demonstrated significant potential for improving the accuracy and efficiency of computer-aided diagnostic systems. This study presents a hybrid deep learning framework for automated bone cancer detection and multi-stage classification using radiological imaging. The proposed framework incorporates image preprocessing, region-of-interest segmentation, handcrafted texture feature extraction, and hybrid deep learning-based classification to distinguish healthy bone tissue from malignant tumors across four clinical stages (Stage I-IV). A dataset comprising 2,500 radiological images obtained from publicly available bone tumor repositories and collaborating healthcare institutions was used for model development and evaluation. Experimental results demonstrated an overall classification accuracy of 98.41%, sensitivity of 97.92%, specificity of 98.76%, precision of 98.18%, F1-score of 98.05%, and an area under the receiver operating characteristic curve (AUC) of 0.991. Comparative evaluation against conventional machine learning models, including Random Forest, K-Nearest Neighbors, and Support Vector Machine classifiers, showed improved diagnostic performance of the proposed framework. The proposed approach has the potential to support clinicians by facilitating early detection, accurate disease staging, and timely therapeutic decision-making. These findings suggest that AI-assisted diagnostic systems may enhance computer aided assessment of bone malignancies and contribute to improved clinical workflow and patient management in orthopedic oncology.